captchasonic-solve

captchasonic-solve is a skill for Claude Code from Captcha-Sonic/Agent-skills. It costs 68 tokens per session (1,293 once invoked), scanned A, original, MIT.

A guide for sending a CAPTCHA image, URL, or encoded data to CaptchaSonic, an online CAPTCHA-solving service, through its MCP server. It explains how to select the service’s type parameter for different CAPTCHA systems.

In plain words
What is it for?
It is for solving supported CAPTCHA types such as reCAPTCHA, Cloudflare Turnstile, Geetest, AWS WAF, TikTok, Binance, and text recognition.
Why use it?
It helps an agent provide the required input and choose the correct request type for image, token, slide, grid, or OCR challenges.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the captchasonic plugin — 4 skills, 1 MCP server shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/captcha-sonic/agent-skills/captchasonic-solve
Any agent
npx skills add Captcha-Sonic/Agent-skills --skill captchasonic-solve
Clone the repo
git clone --depth 1 https://github.com/Captcha-Sonic/Agent-skills

Made for: Claude Code.

Or install captchasonic, the plugin that ships this one along with the rest of its 4 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for captchasonic-solve

README.md
[![agentmods](https://agentmods.dev/badge/skills/captcha-sonic/agent-skills/captchasonic-solve.svg)](https://agentmods.dev/skills/captcha-sonic/agent-skills/captchasonic-solve)
Your own site
<a href="https://agentmods.dev/skills/captcha-sonic/agent-skills/captchasonic-solve"><img src="https://agentmods.dev/badge/skills/captcha-sonic/agent-skills/captchasonic-solve.svg" alt="Measured on agentmods" height="20"></a>
Per session 68 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,293 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00068 $0.01293
Opus 5 $0.00034 $0.00647
Sonnet 5 $0.00014 $0.00259
Haiku 4.5 $0.00007 $0.00129

Measured 5d ago against content hash f97328e2bd51, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

captchasonic-solve scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/captchasonic-solve/SKILL.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Solve a CAPTCHA with CaptchaSonic

Use the CaptchaSonic MCP solve_captcha tool to solve any supported CAPTCHA type.

Prerequisites

The CaptchaSonic MCP server must be connected. If not set up yet, read references/mcp-setup.md or use the captchasonic-setup skill first.

Step 1: Identify the CAPTCHA Type

Determine the correct type parameter from the user's request:

User Says type Parameter Category
"PopularCaptcha grid" / "select all X" PopularCaptchaImage Image (sync)
"reCAPTCHA v2 grid" PopularCaptchaImage Image (sync)
"Geetest slide" geetest_slide Image (sync)
"Geetest click" geetest_click Image (sync)
"Geetest nine-grid" geetest_nine Image (sync)
"OCR" / "text captcha" ocr Image (sync)
"AWS WAF" aws Image (sync)
"TikTok" tiktok Image (sync)
"Binance slide" binance Image (sync)
"Cloudflare Turnstile" turnstile Token (async)
"reCAPTCHA v2 token" recaptcha_v2 Token (async)
"reCAPTCHA v3 token" recaptcha_v3 Token (async)

Step 2: Gather Required Information

For image-based CAPTCHAs (sync):

  • type — the captcha type from the table above
  • question — the challenge text shown to the user (e.g., "Select all traffic lights")
  • image_base64 — base64-encoded PNG/JPEG image bytes
    • OR image_url — public URL of the captcha image

For token-based CAPTCHAs (async):

  • type — the captcha type (e.g., turnstile)
  • question — can be empty or describe the task
  • website_url — the page URL where the captcha appears

Step 3: Call the MCP Tool

Use the solve_captcha MCP tool with the gathered parameters.

Example for image captcha:

Tool: solve_captcha
Arguments:
  type: "PopularCaptchaImage"
  question: "Select all traffic lights"
  image_base64: "<base64 encoded image>"

Example for token captcha:

Tool: solve_captcha
Arguments:
  type: "turnstile"
  question: "Cloudflare Turnstile"
  website_url: "https://example.com"

Read the full file on GitHub · 132 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 132 lines · 68 tokens per session scan A f97328e2bd51

Subscribe to this mod's changes

captchasonic-solve is a skill published in the GitHub repository Captcha-Sonic/Agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,293 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

fetch-crawl4ai

Deep URL fetch using crawl4ai (Playwright-powered) for JS-rendered pages, anti-bot sites, and dynamic content. Slower than fetch-jina but handles sites that block simple fetchers. Requires user-installed crawl4ai package.

0xmariowu/Autosearch · 56 tokens

auto-captcha-solver

Universal captcha auto-solver for Playwright browser automation. Detects hCaptcha and reCAPTCHA v2 on any page, solves via NopeCHA API, and injects tokens automatically. Drop-in CaptchaSolver class with autosolve(page) method.

interfluve-wav/auto-captcha-solver · 57 tokens

playwright-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

valarpirai/code-graph · 52 tokens

chrome-devtools-cli

Use this skill to write shell scripts or run shell commands to automate tasks in the browser or otherwise use Chrome DevTools via CLI.

ChromeDevTools/chrome-devtools-mcp · 31 tokens

a11y-debugging

Uses Chrome DevTools MCP for accessibility (a11y) debugging and auditing based on web.dev guidelines. Use when testing semantic HTML, ARIA labels, focus states, keyboard navigation, tap targets, and color contrast.

ChromeDevTools/chrome-devtools-mcp · 50 tokens

chrome-devtools

Uses Chrome DevTools via MCP for efficient debugging, troubleshooting and browser automation. Use when debugging web pages, automating browser interactions, analyzing performance, or inspecting network requests. This skill does not apply to --slim mode (MCP configuration).

ChromeDevTools/chrome-devtools-mcp · 55 tokens